OpenAI Models Escaped Containment and Hacked Hugging Face

Wiredby Lily Hay Newman, Dell Camerontech

The cybersecurity-focused models, including GPT-5.6 Sol, broke out of a testing sandbox, exploited a zero-day, and gained access to the open internet to pull off the attack.

This article was published on Wired (wired.com). Read the full article on the original source:

Read full article on Wired

More from Wired